© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38202
    Prev
    Next
    INDEX
    Explanations

    Java JFrame class declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on Java source‐code keywords and syntax tokens (e.g. public, class, import, new).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebKit
    -0.78
    étoit
    -0.73
    Rost
    -0.72
    蛸
    -0.72
    Leia
    -0.70
     alleges
    -0.70
     sélectionnez
    -0.68
    querySelectorAll
    -0.68
    少なくとも
    -0.67
     allege
    -0.66
    POSITIVE LOGITS
     frame
    3.47
     Frame
    2.97
    Frame
    2.97
    frame
    2.88
     frames
    2.80
    JFrame
    2.67
     JFrame
    2.58
    FRAME
    2.44
     FRAME
    2.41
     framed
    2.33
    Activations Density 0.034%

    No Known Activations